{"id":"W2039112550","doi":"10.1016/j.acra.2014.09.001","title":"Methods and Challenges in Quantitative Imaging Biomarker Development","year":2014,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Biomarker; Alliance; Medicine; Imaging biomarker; Field (mathematics); Radiomics; Task (project management); Task force; Biomarker discovery; Engineering ethics; Medical physics; Data science; Radiology; Computer science; Political science; Magnetic resonance imaging; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004044683,0.0004377845,0.002723509,0.001404507,0.00005125542,0.000006394835,0.0002280829,0.000662235,0.00001736524],"category_scores_gemma":[0.001971049,0.0003304405,0.0001489692,0.0003808053,0.0003325227,0.00003946065,0.0001474237,0.002489732,0.00002376914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001333522,"about_ca_system_score_gemma":0.0002320942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001197864,"about_ca_topic_score_gemma":9.636565e-7,"domain_scores_codex":[0.9962993,0.001308415,0.001004341,0.0007574746,0.0001253948,0.0005051014],"domain_scores_gemma":[0.997209,0.001936823,0.0003643561,0.0002579849,0.00002433957,0.0002075028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008557637,0.000008493868,0.0001548356,0.00741247,0.0001466899,0.0000584508,0.0003741069,1.339223e-7,0.000006821867,0.001387533,0.0003909251,0.990051],"study_design_scores_gemma":[0.0004498275,0.0000291576,0.0003867893,0.00821013,0.0002854338,0.002538411,0.00005507008,0.0007916746,5.052065e-7,0.0001924197,0.9867619,0.0002986484],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002970161,0.9932435,0.001967531,0.002490975,0.0003300478,0.0004652886,7.929092e-7,0.00005011016,0.001422078],"genre_scores_gemma":[0.000005578723,0.9426759,0.05646245,0.0004128188,0.0001575212,0.00009058262,0.00003887923,0.00006702118,0.00008927732],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9897524,"threshold_uncertainty_score":0.9999148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1674750355527222,"score_gpt":0.4854903350973562,"score_spread":0.3180152995446339,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}